English
Related papers

Related papers: Speech-text based multi-modal training with bidire…

200 papers

While automatic speech recognition (ASR) greatly benefits from data augmentation, the augmentation recipes themselves tend to be heuristic. In this paper, we address one of the heuristic approach associated with balancing the right amount…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-17 Vishwanath Pratap Singh , Federico Malato , Ville Hautamaki , Md. Sahidullah , Tomi Kinnunen

State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usually modeled via attention mechanisms, which are…

Computation and Language · Computer Science 2023-05-30 Florian Mai , Juan Zuluaga-Gomez , Titouan Parcollet , Petr Motlicek

Attention-based models have made tremendous progress on end-to-end automatic speech recognition(ASR) recently. However, the conventional transformer-based approaches usually generate the sequence results token by token from left to right,…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-12 Xi Chen , Songyang Zhang , Dandan Song , Peng Ouyang , Shouyi Yin

We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct a temporal slice of filterbank features from past…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-15 Shaoshi Ling , Yuzong Liu , Julian Salazar , Katrin Kirchhoff

Conditional sound separation in multi-source audio mixtures without having access to single source sound data during training is a long standing challenge. Existing mix-and-separate based methods suffer from significant performance drop…

Sound · Computer Science 2024-04-03 Tanvir Mahmud , Saeed Amizadeh , Kazuhito Koishida , Diana Marculescu

Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing.…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-28 Thai-Son Nguyen , Ngoc-Quan Pham , Sebastian Stueker , Alex Waibel

Recent advances in speech recognition and translation rely on hundreds of thousands of hours of Internet speech data. We argue that state-of-the art accuracy can be reached without relying on web-scale data. Canary - multilingual ASR and…

Self-supervised learning of speech representations has achieved impressive results in improving automatic speech recognition (ASR). In this paper, we show that data selection is important for self-supervised learning. We propose a simple…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-06 Zhiyun Lu , Yongqiang Wang , Yu Zhang , Wei Han , Zhehuai Chen , Parisa Haghani

One solution to automatic speech recognition (ASR) of overlapping speakers is to separate speech and then perform ASR on the separated signals. Commonly, the separator produces artefacts which often degrade ASR performance. Addressing this…

Most spoken language understanding systems use a pipeline approach composed of an automatic speech recognition interface and a natural language understanding module. This approach forces hard decisions when converting continuous inputs into…

Computation and Language · Computer Science 2023-10-18 Quentin Meeus , Marie-Francine Moens , Hugo Van hamme

Speaker-attributed automatic speech recognition (SA-ASR) aims to transcribe speech while assigning transcripts to the corresponding speakers accurately. Existing methods often rely on complex modular systems or require extensive fine-tuning…

Computation and Language · Computer Science 2025-01-16 Thai-Binh Nguyen , Alexander Waibel

The last year has seen astonishing progress in text-prompted image generation premised on the idea of a cross-modal representation space in which the text and image domains are represented jointly. In ASR, this idea has found application as…

Computation and Language · Computer Science 2023-08-14 Cal Peyser , Zhong Meng , Ke Hu , Rohit Prabhavalkar , Andrew Rosenberg , Tara N. Sainath , Michael Picheny , Kyunghyun Cho

Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…

Computation and Language · Computer Science 2019-04-11 Yi-Chen Chen , Sung-Feng Huang , Hung-yi Lee , Lin-shan Lee

Spatial information is a critical clue for multi-channel multi-speaker target speech recognition. Most state-of-the-art multi-channel Automatic Speech Recognition (ASR) systems extract spatial features only during the speech separation…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-27 Yiwen Shao , Yong Xu , Sanjeev Khudanpur , Dong Yu

Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resource scenarios. One solution to tackle this issue is to…

Computation and Language · Computer Science 2021-07-14 Nick Rossenbach , Mohammad Zeineldeen , Benedikt Hilmes , Ralf Schlüter , Hermann Ney

We present a new end-to-end architecture for automatic speech recognition (ASR) that can be trained using \emph{symbolic} input in addition to the traditional acoustic input. This architecture utilizes two separate encoders: one for…

Computation and Language · Computer Science 2018-06-19 Adithya Renduchintala , Shuoyang Ding , Matthew Wiesner , Shinji Watanabe

Automatic Speech Recognition (ASR) systems, despite large multilingual training, struggle in low-resource scenarios where labeled data is scarce. We propose BEARD (BEST-RQ Encoder Adaptation with Re-training and Distillation), a novel…

Computation and Language · Computer Science 2026-05-13 Raphaël Bagat , Irina Illina , Emmanuel Vincent

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

Artificial Intelligence · Computer Science 2021-03-19 Md Akmal Haidar , Chao Xing , Mehdi Rezagholizadeh

In this paper, we explore an improved framework to train a monoaural neural enhancement model for robust speech recognition. The designed training framework extends the existing mixture invariant training criterion to exploit both unpaired…

Sound · Computer Science 2022-09-21 Jisi Zhang , Catalin Zorila , Rama Doddipatla , Jon Barker

In sequence-to-sequence Transformer ASR, autoregressive (AR) models achieve strong accuracy but suffer from slow decoding, while non-autoregressive (NAR) models enable parallel decoding at the cost of degraded performance. We propose a…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-26 Hao Yen , Pin-Jui Ku , Ante Jukić , Sabato Marco Siniscalchi